AttributeError: 'Tensor' 对象没有属性 '_keras_history' [英] AttributeError: 'Tensor' object has no attribute '_keras_history'

问题描述

我查找了所有'Tensor' 对象没有属性 ***"，但似乎没有一个与 Keras 相关(除了 TensorFlow: AttributeError: 'Tensor' object has no attribute 'log10' 这没有帮助)...

I looked for all the "'Tensor' object has no attribute ***" but none seems related to Keras (except for TensorFlow: AttributeError: 'Tensor' object has no attribute 'log10' which didn't help)...

我正在制作一种 GAN(生成对抗网络).在这里你可以找到结构.

I am making a sort of GAN (Generative Adversarial Networks). Here you can find the structure.

Layer (type)                     Output Shape          Param #         Connected to                     
_____________________________________________________________________________
input_1 (InputLayer)             (None, 30, 91)        0                                            
_____________________________________________________________________________
model_1 (Model)                  (None, 30, 1)         12558           input_1[0][0]                    
_____________________________________________________________________________
model_2 (Model)                  (None, 30, 91)        99889           input_1[0][0]                    
                                                                       model_1[1][0]                    
_____________________________________________________________________________
model_3 (Model)                  (None, 1)             456637          model_2[1][0]                    
_____________________________________________________________________________

我预训练了 model_2 和 model_3.问题是我使用由 0 和 1 组成的列表对 model_2 进行了预训练，但是 model_1 返回了接近的值.所以我考虑使用以下代码对 model1_output 进行四舍五入:model1_out 上的 K.round().

I pretrained model_2, and model_3. The thing is I pretrained model_2 with list made of 0 and 1, but model_1 return approached values. So i considered rounding the model1_output, with the following code : the K.round() on model1_out.

import keras.backend as K
[...]
def make_gan(GAN_in, model1, model2, model3):
    model1_out = model1(GAN_in)
    model2_out = model2([GAN_in, K.round(model1_out)])
    GAN_out = model3(model2_out)
    GAN = Model(GAN_in, GAN_out)
    GAN.compile(loss=loss, optimizer=model1.optimizer, metrics=['binary_accuracy'])
    return GAN
[...]

我有以下错误:

AttributeError: 'Tensor' 对象没有属性 '_keras_history'

AttributeError: 'Tensor' object has no attribute '_keras_history'

完整回溯:

Traceback (most recent call last):
  File "C:UsersAsmaaDocumentsBillyValuationGFD.py", line 88, in <module>
GAN = make_gan(inputSentence, G, F, D)
  File "C:UsersAsmaaDocumentsBillyValuationGFD.py", line 61, in make_gan
GAN = Model(GAN_in, GAN_out)
  File "C:ProgramDataAnaconda3libsite-packageskeraslegacyinterfaces.py", line 88, in wrapper
return func(*args, **kwargs)
  File "C:ProgramDataAnaconda3libsite-packageskerasengine	opology.py", line 1705, in __init__
build_map_of_graph(x, finished_nodes, nodes_in_progress)
  File "C:ProgramDataAnaconda3libsite-packageskerasengine	opology.py", line 1695, in build_map_of_graph
layer, node_index, tensor_index)
  File "C:ProgramDataAnaconda3libsite-packageskerasengine	opology.py", line 1695, in build_map_of_graph
layer, node_index, tensor_index)
  File "C:ProgramDataAnaconda3libsite-packageskerasengine	opology.py", line 1665, in build_map_of_graph
layer, node_index, tensor_index = tensor._keras_history
AttributeError: 'Tensor' object has no attribute '_keras_history'

我在 Windows 7 上使用 Python 3.6 和 Spyder 3.1.4.上周我用 pip 升级了 TensorFlow 和 Keras.感谢您提供的任何帮助！

I'm using Python 3.6, with Spyder 3.1.4, on Windows 7. I upgraded TensorFlow and Keras with pip last week. Thank you for any help provided !

推荐答案

我的问题是在 keras 上使用 '+' 而不是 'Add'

My problem was using '+' instead of 'Add' on keras

这篇关于AttributeError: 'Tensor' 对象没有属性 '_keras_history'的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！